Skip to content

Agentkit

Agentkit is a lightweight, model-agnostic framework for building AI agents in Python. The language model decides what tools to call, in what order, until it reaches a final answer — no brittle chains or rigid pipelines needed.

What you can build

PatternDescription
Conversational assistantsSingle-agent chatbots that call tools
Autonomous task agentsMulti-step reasoning with memory and state
Multi-agent systemsGraphs of agents that collaborate or compete

Key features

FeatureDescription
Model AgnosticAmazon Bedrock, Anthropic, OpenAI, Gemini, Ollama, LiteLLM, and more
Tool systemPython decorators, directory hot-reload, MCP server support
Multi-agentGraph (deterministic) and Swarm (autonomous) patterns
StreamingAsync token streaming
HooksStrongly-typed lifecycle events for observability and control
SessionsBuilt-in conversation persistence with file, S3, or custom backends
CheckpointsThin ReAct-loop bookmarks for mid-tool crash recovery under a session
PermissionsDeclarative allow / deny / interrupt rules for host files and commands
ObservabilityOpenTelemetry tracing and metrics out of the box

Minimal example

Default model is Amazon Bedrock

Agent() with no model= uses Amazon Bedrock (Claude Sonnet 4.6 in us-west-2). Configure AWS credentials (aws configure or AWS_* env vars), or pass an explicit model — see Installation and Model Providers.

python
from elsai import Agent

agent = Agent()
agent("Explain quantum entanglement in one paragraph")

Every additional capability — tools, memory, multi-agent orchestration — layers on top without rewriting existing code.

Installation

bash
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.3.1
pip install --extra-index-url https://core-packages.elsai.ai/root/ "elsai-model[bedrock]==2.1.0"

For other providers, install the matching extra (for example "elsai-model[openai]==2.1.0"). See Installation.

Next steps

Copyright © 2026 elsai foundry.